Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add byx-darwin/gitflow-cli --skill gf-smellgit clone --depth 1 https://github.com/byx-darwin/gitflow-cliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/byx-darwin/gitflow-cli/gf-smell)<a href="https://agentmods.dev/skills/byx-darwin/gitflow-cli/gf-smell"><img src="https://agentmods.dev/badge/skills/byx-darwin/gitflow-cli/gf-smell/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/byx-darwin/gitflow-cli/gf-smell"><img src="https://agentmods.dev/badge/skills/byx-darwin/gitflow-cli/gf-smell.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.03405 |
| Opus 5.5 | $0.00028 | $0.01362 |
| Sonnet 5.5 | $0.00014 | $0.00681 |
| Haiku 4.5 | $0.00007 | $0.00341 |
Grade A, and why
gf-smell scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gf-smell — Code Smell & Complexity Hotspot Detection
Three-stage judgement protocol: candidate → verify → confirm. Language-agnostic
protocol in this file; language-specific detection in references/<lang>.md.
Detection only — never auto-fix. This skill writes its report to docs/,
so it does not use the read-only permission profile.
Preconditions
- Read access to the target source tree
- The language layer's tooling installed (see
references/<lang>.md); missing tools degrade, never improvise
When to Use
| English | 中文 | Context |
|---|---|---|
| code smell detection | 代码坏味道检测 | find structural problems |
| complexity hotspots | 复杂度热点 | which code is hardest to change |
| long function / deep nesting | 超长函数 / 深层嵌套 | threshold-based scan |
| god structure | 上帝结构 | too many responsibilities in one unit |
| refactor candidates | 重构候选 | where to start refactoring |
When NOT to Use
| Scenario | Why Not | Use Instead |
|---|---|---|
| Fixing the smells found | This skill detects and reports only | /gf-refactor for behavior-preserving fixes, or /gf-workflow for the full pipeline |
| Pre-delivery quality gate | This skill measures structure, not gate pass/fail | /gf-quality |
| Secret / vulnerability scanning | Different problem class | /gf-security-check |
| Reviewing a PR diff | This skill scans a tree, not a diff verdict | /gf-pr-review |
| Lowering thresholds to silence findings | This skill never edits policy configuration | User decides after reviewing the report |
Core Rule: A Threshold Breach Is a Candidate, Not a Conclusion
Every number a tool emits is a candidate signal. It becomes a finding only after Stage 2 verification reads the actual code. Reporting raw tool output as findings is the single most common failure of this skill.
Stage 0: Scope
Resolve the scan scope before running anything.
- User-specified path or diff range; default is the whole source tree.
- Always exclude these directories — they contain build output, vendored code, or working-tree copies that would triple-count the same file:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 24d ago Changed · +2 lines 304b079180da
- 28d ago Changed · +1 lines f5bb78b0225c
- 29d ago First seen · 340 lines · 71 tokens per session scan A 04a1408692a2
gf-smell is a skill published in the GitHub repository byx-darwin/gitflow-cli (3 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 3,405 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…